Common domain shift problem formulations consider the integration of multiple source domains, or the target domain during training. Regarding the generalization of machine learning models between different car interiors, we formulate the criterion of training in a single vehicle: without access to the target distribution of the vehicle the model would be deployed to, neither with access to multiple vehicles during training. We performed an investigation on the SVIRO dataset for occupant classification on the rear bench and propose an autoencoder based approach to improve the transferability. The autoencoder is on par with commonly used classification models when trained from scratch and sometimes out-performs models pre-trained on a large amount of data. Moreover, the autoencoder can transform images from unknown vehicles into the vehicle it was trained on. These results are corroborated by an evaluation on real infrared images from two vehicle interiors.
Autoencoder Based Inter-Vehicle Generalization for In-Cabin Occupant Classification
2021 IEEE Intelligent Vehicles Symposium (IV) ; 1296-1303
2021-07-11
3633692 byte
Conference paper
Electronic Resource
English
AUTOENCODER BASED INTER-VEHICLE GENERALIZATION FOR IN-CABIN OCCUPANT CLASSIFICATION
British Library Conference Proceedings | 2021
|Artificial Intelligence-based Vehicle In-Cabin Occupant Detection and Classification System
Springer Verlag | 2022
|SYSTEMS AND METHODS FOR VEHICLE OCCUPANT CLASSIFICATION USING IN-CABIN SENSING
European Patent Office | 2024
|